Large Multivariate Time Series Forecasting

Abstract

Research on the analysis of time series has gained momentum in recent years, as knowledge derived from time series analysis can improve the decision-making process for industrial and scientific fields. Furthermore, time series analysis is often an essential part of business intelligence systems. With the growing interest in this topic, a novel set of challenges emerges. Utilizing forecasting models that can handle a large number of predictors is a popular approach that can improve results compared to univariate models. However, issues arise for high dimensional data. Not all variables will have direct impact on the target variable and adding unrelated variables may make the forecasts less accurate. Thus, the authors explore methods that can effectively deal with time series with many predictors. The authors discuss state-of-the-art methods for optimizing the selection, dimension reduction, and shrinkage of predictors. While similar research exists, it exclusively targets small and medium datasets, and thus, the research aims to fill the knowledge gap in the context of big data applications.

A Hybrid Approach for Forecasting Occupancy of Building’s Multiple Space Types

“…The IBk with WSE has performed well as compared to other techniques [29]. The authors in [30], proposed a feature selection method that can be used for time series forecasting using clustering technique. Furthermore, the method is compared with Principal Component Analysis (PCA) and kernel PCA.…”

Improving the Understanding, Diagnostics, and Prediction of Precipitation

“…Second, SVR was used with the default hyperparameters in selecting predictors through SFS. Other selection methods [78][79][80][81][82][83] could be tested in future studies, as well as other learning algorithms that serve as scoring functions (e.g., random forests) performing a hyperparameter tuning. The former would help analyze the most relevant indices that influence the study area more exhaustively and with greater significance.…”

Explorando causalidade na seleção de variáveis para previsão de séries temporais multivariadas

“…Ele se baseia na ideia de que uma série temporal X causa outra série temporal Y se a inclusão do histórico de X melhora a previsão de Y em comparac ¸ão com um modelo que usa apenas o histórico de Y . Exemplos de trabalhos que usam métodos baseados em Causalidade de Granger para selec ¸ão de características em séries temporais são: [15], [16] e [17].…”